liteparse
Local document extraction with no API key — read the file, not the whole file.
Install
$ npx skills add run-llama/llamaparse-agent-skills --skill liteparseNeeds Node 18+ and @llamaindex/liteparse. No API key — unlike the llamaparse skill in the same repo.
Best for
Looking up a figure or table inside a large document without burning context on the parts you do not need.
Not ideal for
Complex layout reconstruction or scanned-image OCR — the hosted llamaparse skill in the same repo is the heavier option for that.
About this skill
Use when a task involves reading a PDF, DOCX, PPTX, XLSX, or image and pulling text, tables, or specific values out of it. Fast, local, model-free extraction through the lit CLI, with low-cost search patterns instead of loading whole documents into context.
Score breakdown
Score breakdown
rubric 1.0Composite 0–100 score derived from 9 verifiable signals. See the rubric →
Related skills
Extract, fill, merge. PDF manipulation with bundled scripts so Claude does not waste tokens generating them.
Word documents end-to-end. Create, edit, comment, track-change.
Excel spreadsheets with real formulas, charts, and formatting — not flat CSV exports.